Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Tokpo, Ewoenam"'
Autor:
Tokpo, Ewoenam Kwaku, Calders, Toon
Despite the evolution of language models, they continue to portray harmful societal biases and stereotypes inadvertently learned from training data. These inherent biases often result in detrimental effects in various applications. Counterfactual Dat
Externí odkaz:
http://arxiv.org/abs/2407.16431
Autor:
Tokpo, Ewoenam Kwaku, Calders, Toon
Counterfactual Data Augmentation (CDA) has been one of the preferred techniques for mitigating gender bias in natural language models. CDA techniques have mostly employed word substitution based on dictionaries. Although such dictionary-based CDA tec
Externí odkaz:
http://arxiv.org/abs/2311.03186
To mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text classificati
Externí odkaz:
http://arxiv.org/abs/2301.12855
Autor:
Tokpo, Ewoenam Kwaku, Calders, Toon
It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Although many such texts contain stereotypes and biases that inherently exist in natural language for reasons that are
Externí odkaz:
http://arxiv.org/abs/2201.08643
An increasing awareness of biased patterns in natural language processing resources, like BERT, has motivated many metrics to quantify `bias' and `fairness'. But comparing the results of different metrics and the works that evaluate with such metrics
Externí odkaz:
http://arxiv.org/abs/2112.07447